Hi,I was able to solve the segmentation fault issue. It was because of OOVs. I’m currently trying to tune the parameters using mert, but it is running extremely slow. For example, from the logs: Translating: 美国 之 音 记者 伏 来 库 斯 从 布宜诺斯艾利斯 发 来 的 另 一 篇 报导 说 , 几 名 美国 国会 议员 星期二 把 这 一 争论 带 到 了 布宜诺斯艾利斯 的 会议
Hi,
There are a few differences, most of which I'd expect you're fine with.
- The discounts are different but you're using --discount_fallback so
you know that.
- Unknown word handling is different. If you want an SRI's IMHO broken
behavior pass --interpolate_unigrams 0 (though if your
Hi,
Does anyone know if there are any gotchas using lmplz instead of
ngram-count during transliteration model training? I'm trying it out
using the --discount_fallback option and lmplz's default behavior should
match the -interpolate option for ngram-count (I think?)
Thanks!
-Jeremy
__
**
Second Call for Papers
EAMT 2016, Riga, Latvia - http://eamt2016.tilde.com/
19th Conference of the European Association for Machine Translation
Again just badly written multithreading. It is still much faster than
processPhraseTableMin, isn't EMS running them in parallel or something?
(I don't use EMS).
On 18.02.2016 08:59, Vincent Nguyen wrote:
> yeah but then if in EMS we want to use ProcessPhrasetablemin with 8 threads
> and ProcessL
yeah but then if in EMS we want to use ProcessPhrasetablemin with 8 threads
and ProcessLexicalTableMin with 4 threads, difficult, right ?
just letting you know, with 8 threads the processlexicaltablemin seems
to run with 1 thread only .
Le 17/02/2016 23:16, Marcin Junczys-Dowmunt a écrit